The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill guides an agent to process various project manifests and configuration files which serve as potential ingestion points for untrusted data.
Ingestion points: The agent is instructed to read package.json, pnpm-workspace.yaml, tsconfig.json, vitest.config.ts, and other tool-specific configuration files as part of the registration and audit process (detailed in registration.md and SKILL.md).
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions when reading these repository files.
Capability inventory: The agent has the capability to execute pnpm install, run package tests, execute build scripts, and perform code generation (SKILL.md).
Sanitization: The instructions do not describe specific sanitization or validation steps for the content of these manifests before processing.
[COMMAND_EXECUTION]: The skill requires the execution of shell-based development tools to perform its primary function.
Evidence: The workflow includes running pnpm install for dependency management, executing package-specific tests and scripts, running codegen for barrel generation, and performing dry packing for publication validation (SKILL.md, dependencies.md, publishing.md). These actions are aligned with the intended purpose of package maintenance.

package-development